Spaces:
Running
Running
| # import gradio as gr | |
| # import pandas as pd | |
| # from sentence_transformers import SentenceTransformer, util | |
| # # Load files | |
| # df = pd.read_excel("IslamWeb_output.xlsx") | |
| # df2 = pd.read_excel("JordanFatwas_all.xlsx") | |
| # # Validate | |
| # for d, name in [(df, "IslamWeb"), (df2, "JordanFatwas")]: | |
| # if not {"question", "link"}.issubset(d.columns): | |
| # raise ValueError(f"❌ Missing required columns in {name}") | |
| # # Load model + encode | |
| # model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2") | |
| # embeddings = model.encode(df["question"].fillna('').tolist(), convert_to_tensor=True) | |
| # embeddings2 = model.encode(df2["question"].fillna('').tolist(), convert_to_tensor=True) | |
| # # Define function | |
| # def search_fatwa(query): | |
| # query_embedding = model.encode(query, convert_to_tensor=True) | |
| # scores = util.pytorch_cos_sim(query_embedding, embeddings)[0] | |
| # top_idx = int(scores.argmax()) | |
| # scores2 = util.pytorch_cos_sim(query_embedding, embeddings2)[0] | |
| # top_idx2 = int(scores2.argmax()) | |
| # return { | |
| # "question1": df.iloc[top_idx]["question"], | |
| # "link1": df.iloc[top_idx]["link"], | |
| # "question2": df2.iloc[top_idx2]["question"], | |
| # "link2": df2.iloc[top_idx2]["link"], | |
| # } | |
| # # Interface | |
| # iface = gr.Interface( | |
| # fn=search_fatwa, | |
| # inputs="text", | |
| # outputs="json", | |
| # allow_flagging="never", | |
| # title="Fatwa Search (Dual Source)", | |
| # description="Get the most relevant fatwas from both datasets" | |
| # ) | |
| # iface.launch() | |
| # import torch | |
| # import pandas as pd | |
| # from sentence_transformers import SentenceTransformer, util | |
| # import gradio as gr | |
| # model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2") | |
| # df = pd.read_csv("cleaned1.csv") | |
| # df2 = pd.read_csv("cleaned2.csv") | |
| # embeddings = torch.load("embeddings1.pt") | |
| # embeddings2 = torch.load("embeddings2.pt") | |
| # # def search_fatwa(data): | |
| # # query = data[0] if data else "" | |
| # # query_embedding = model.encode(query, convert_to_tensor=True) | |
| # # top_idx = int(util.pytorch_cos_sim(query_embedding, embeddings)[0].argmax()) | |
| # # top_idx2 = int(util.pytorch_cos_sim(query_embedding, embeddings2)[0].argmax()) | |
| # # return { | |
| # # "question1": df.iloc[top_idx]["question"], | |
| # # "link1": df.iloc[top_idx]["link"], | |
| # # "question2": df2.iloc[top_idx2]["question"], | |
| # # "link2": df2.iloc[top_idx2]["link"] | |
| # # } | |
| # def search_fatwa(data): | |
| # query = data[0] if isinstance(data, list) else data | |
| # if not query: | |
| # return {"question1": "", "link1": "", "question2": "", "link2": ""} | |
| # query_embedding = model.encode(query, convert_to_tensor=True) | |
| # top_idx = int(util.pytorch_cos_sim(query_embedding, embeddings)[0].argmax()) | |
| # top_idx2 = int(util.pytorch_cos_sim(query_embedding, embeddings2)[0].argmax()) | |
| # # return { | |
| # # "question1": df.iloc[top_idx]["question"], | |
| # # "link1": df.iloc[top_idx]["link"], | |
| # # "question2": df2.iloc[top_idx2]["question"], | |
| # # "link2": df2.iloc[top_idx2]["link"] | |
| # # } | |
| # result = f"""Question 1: {df.iloc[top_idx]["question"]} | |
| # Link 1: {df.iloc[top_idx]["link"]} | |
| # Question 2: {df2.iloc[top_idx2]["question"]} | |
| # Link 2: {df2.iloc[top_idx2]["link"]}""" | |
| # return result | |
| # iface = gr.Interface( | |
| # fn=search_fatwa, | |
| # inputs=[gr.Textbox(label="text", lines=3)], | |
| # outputs="text" # Changed from "json" to "text" | |
| # ) | |
| # # iface = gr.Interface(fn=search_fatwa, inputs=[gr.Textbox(label="text", lines=3)], outputs="json") | |
| # # iface = gr.Interface( | |
| # # fn=predict, | |
| # # inputs=[gr.Textbox(label="text", lines=3)], | |
| # # outputs='text', | |
| # # title=title, | |
| # # ) | |
| # iface.launch() | |
| import torch | |
| import pandas as pd | |
| from sentence_transformers import SentenceTransformer, util | |
| import gradio as gr | |
| model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2") | |
| df = pd.read_csv("cleaned1.csv") | |
| df2 = pd.read_csv("cleaned2.csv") | |
| embeddings = torch.load("embeddings1.pt") | |
| embeddings2 = torch.load("embeddings2.pt") | |
| def predict(text): | |
| if not text or text.strip() == "": | |
| return "No query provided" | |
| query_embedding = model.encode(text, convert_to_tensor=True) | |
| top_idx = int(util.pytorch_cos_sim(query_embedding, embeddings)[0].argmax()) | |
| top_idx2 = int(util.pytorch_cos_sim(query_embedding, embeddings2)[0].argmax()) | |
| result = f"""Question 1: {df.iloc[top_idx]["question"]} | |
| Link 1: {df.iloc[top_idx]["link"]} | |
| Question 2: {df2.iloc[top_idx2]["question"]} | |
| Link 2: {df2.iloc[top_idx2]["link"]}""" | |
| return result | |
| # Match the EXACT structure of your working translation app | |
| title = "Search CSV" | |
| iface = gr.Interface( | |
| fn=predict, # Changed from search_fatwa to predict | |
| inputs=[gr.Textbox(label="text", lines=3)], | |
| outputs='text', | |
| title=title, | |
| ) | |
| iface.launch() |